Handwritten stroke augmentation on images
Abstract: In this paper, we introduce Handwritten stroke augmentation, a new data augmentation for handwritten character images. This method focuses on augmenting handwritten image data by altering the shape of input character strokes in training. The proposed handwritten augmentation is similar to position augmentation, color augmentation for images but a deeper focus on handwritten character strokes. Handwritten stroke augmentation is data-driven, easy to implement, and can be integrated with CNN-based optical character recognition models. Handwritten stroke augmentation can be implemented along with commonly used data augmentation techniques such as cropping, rotating, and yields better performance of models for handwritten image datasets developed using optical character recognition methods. Our source code will be available on GitHub.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: We used updated TMLR style files for this version.
Assigned Action Editor: ~Mathieu_Salzmann1
Submission Number: 1
Loading